Invisible Pedestrians: Synthesizing Adversarial Clothing Textures To Evade Industrial Camera-Based 3D Detection
Lists
Only you see this
Abstract
Recent studies have explored attacking perception models of autonomous driving systems and creating adversarial textures to evade 2D vision or infrared pedestrian detectors. However, purely camera-based 3D detectors remain to be explored, especially in complex real-world traffic scenarios and road conditions where pedestrians are prevalent. In this paper, we propose a pipeline that accurately renders 3D human models onto 2D scenes while maintaining physical realism and spatial coordinate constraints. By leveraging this pipeline, we design a soft-weighted confidence loss to optimize adversarial textures on clothing, effectively suppressing predicted boxes near the human model. A comprehensive evaluation of adversarial textures is conducted on a test set comprising 100 scenes with complex environments. Our attack can consistently evade detection by the industrial camera-based 3D detector SMOKE across multiple viewpoints and scenes.
BibTeX
@inproceedings{ding2024invisible,
author = {Xinlong Ding and Hongwei Yu and Jiansheng Chen and Jinlong Wang and Jintai Du and Huimin Ma},
title = {{Invisible Pedestrians: Synthesizing Adversarial Clothing Textures To Evade Industrial Camera-Based 3D Detection}},
booktitle = {ICME},
year = {2024},
url = {https://openreview.net/forum?id=I7B4T2l1Uv},
}Loading related content...